66 lines
2.7 KiB
Markdown
66 lines
2.7 KiB
Markdown
|
---
|
||
|
|
tags:
|
||
|
|
- vllm
|
||
|
|
- sparsity
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
license: llama3.1
|
||
|
|
base_model: neuralmagic/Sparse-Llama-3.1-8B-2of4
|
||
|
|
datasets:
|
||
|
|
- openai/gsm8k
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
metrics:
|
||
|
|
- accuracy
|
||
|
|
---
|
||
|
|
|
||
|
|
# Sparse-Llama-3.1-8B-gsm8k-2of4
|
||
|
|
|
||
|
|
## Model Overview
|
||
|
|
- **Model Architecture:** Llama-3.1-8B
|
||
|
|
- **Input:** Text
|
||
|
|
- **Output:** Text
|
||
|
|
- **Model Optimizations:**
|
||
|
|
- **Sparsity:** 2:4
|
||
|
|
- **Release Date:** 11/21/2024
|
||
|
|
- **Version:** 1.0
|
||
|
|
- **License(s):** [llama3.1](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)
|
||
|
|
- **Model Developers:** Neural Magic
|
||
|
|
|
||
|
|
This is AI model especialized in grade-school math obtained by fine-tuning the 2:4 sparse [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4) on the [GSM8k](https://huggingface.co/datasets/openai/gsm8k) dataset.
|
||
|
|
It achieves 66.9% 0-shot accuracy on the test set of GSM8k, compared to 66.3% for the fine-tuned dense model [Llama-3.1-8B-gsm8k](https://huggingface.co/neuralmagic/Llama-3.1-8B-gsm8k) — demonstrating over **100% accuracy recovery**.
|
||
|
|
In constrast, the pretrained [Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) achieves 50.7% 5-shot accuracy and the sparse foundational [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4) model achieves 56.3% 5-shot accuracy.
|
||
|
|
|
||
|
|
|
||
|
|
### Model Optimizations
|
||
|
|
|
||
|
|
This inherits the optimizations from its parent, [Sparse-Llama-3.1-8B-2of4](https://huggingface.co/neuralmagic/Sparse-Llama-3.1-8B-2of4).
|
||
|
|
Namely, all linear operators within transformer blocks were pruned to the 2:4 sparsity pattern: in each group of four weights, two are retained while two are pruned.
|
||
|
|
|
||
|
|
|
||
|
|
## Deployment with vLLM
|
||
|
|
|
||
|
|
This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend. vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
|
||
|
|
|
||
|
|
|
||
|
|
## Evaluation
|
||
|
|
|
||
|
|
This model was evaluated on the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
||
|
|
|
||
|
|
### Accuracy
|
||
|
|
#### GSM8k Benchmark
|
||
|
|
<table>
|
||
|
|
<tr>
|
||
|
|
<td><strong>Metric</strong></td>
|
||
|
|
<td style="text-align: center"><strong>Llama-3.1-8B<br>(5-shot)</strong></td>
|
||
|
|
<td style="text-align: center"><strong>Sparse-Llama-3.1-8B-2of4<br>(5-shot)</strong></td>
|
||
|
|
<td style="text-align: center"><strong>Llama-3.1-8B-gsm8k<br>(0-shot)</strong></td>
|
||
|
|
<td style="text-align: center"><strong>Sparse-Llama-3.1-8B-gsm8k-2of4<br>(0-shot)</strong></td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td>Accuracy</td>
|
||
|
|
<td style="text-align: center">50.7%</td>
|
||
|
|
<td style="text-align: center">56.3%</td>
|
||
|
|
<td style="text-align: center">66.3%</td>
|
||
|
|
<td style="text-align: center">66.9%</td>
|
||
|
|
</tr>
|
||
|
|
</table>
|